MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, Yuning Mao


Abstract
Red-teaming is a common practice for mitigating unsafe behaviors in Large Language Models (LLMs), which involves thoroughly assessing LLMs to identify potential flaws and addressing them with responsible and accurate responses.While effective, manual red-teaming is costly, and existing automatic red-teaming typically discovers safety risks without addressing them.In this paper, we propose a Multi-round Automatic Red-Teaming (MART) method, which incorporates both automatic adversarial prompt writing and safe response generation, significantly increasing red-teaming scalability and the safety of the target LLM.Specifically, an adversarial LLM and a target LLM interplay with each other in an iterative manner, where the adversarial LLM aims to generate challenging prompts that elicit unsafe responses from the target LLM, while the target LLM is fine-tuned with safety aligned data on these adversarial prompts. In each round, the adversarial LLM crafts better attacks on the updated target LLM, while the target LLM also improves itself through safety fine-tuning.On adversarial prompt benchmarks, the violation rate of an LLM with limited safety alignment reduces up to 84.7% after 4 rounds of MART, achieving comparable performance to LLMs with extensive adversarial prompt writing. Notably, model helpfulness on non-adversarial prompts remains stable throughout iterations, indicating the target LLM maintains strong performance on instruction following.
Anthology ID:
2024.naacl-long.107
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1927–1937
Language:
URL:
https://aclanthology.org/2024.naacl-long.107
DOI:
10.18653/v1/2024.naacl-long.107
Bibkey:
Cite (ACL):
Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, and Yuning Mao. 2024. MART: Improving LLM Safety with Multi-round Automatic Red-Teaming. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1927–1937, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming (Ge et al., NAACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2024.naacl-long.107.pdf